Adding Evaluation Results

README.md

@@ -4,10 +4,10 @@ language:
 license: other
 tags:
 - uncensored
+base_model: ehartford/Wizard-Vicuna-13B-Uncensored
 datasets:
 - ehartford/wizard_vicuna_70k_unfiltered
 model_name: Wizard Vicuna 13B Uncensored
-base_model: ehartford/Wizard-Vicuna-13B-Uncensored
 inference: false
 model_creator: Eric Hartford
 model_type: llama
@@ -17,6 +17,109 @@ prompt_template: 'A chat between a curious user and an artificial intelligence a
 
   '
 quantized_by: TheBloke
+model-index:
+- name: Wizard-Vicuna-13B-Uncensored-GPTQ
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 29.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 25.47
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 25.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 50.25
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 75.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 9.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ
+      name: Open LLM Leaderboard
 ---
 
 <!-- header start -->
@@ -263,3 +366,17 @@ You are responsible for anything you do with the model, just as you are responsi
 Publishing anything this model generates is the same as publishing it yourself.
 
 You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TheBloke__Wizard-Vicuna-13B-Uncensored-GPTQ)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |36.06|
+|AI2 Reasoning Challenge (25-Shot)|29.61|
+|HellaSwag (10-Shot)              |25.47|
+|MMLU (5-Shot)                    |25.34|
+|TruthfulQA (0-shot)              |50.25|
+|Winogrande (5-shot)              |75.77|
+|GSM8k (5-shot)                   | 9.93|
+